{"id":"https://openalex.org/W4405710098","doi":"https://doi.org/10.1109/iscslp63861.2024.10800051","title":"Constant Q Transform for Audio-Visual Dysarthria Severity Assessment","display_name":"Constant Q Transform for Audio-Visual Dysarthria Severity Assessment","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405710098","doi":"https://doi.org/10.1109/iscslp63861.2024.10800051"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800051","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010332632","display_name":"Guolun Sun","orcid":"https://orcid.org/0000-0002-1840-181X"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guolun Sun","raw_affiliation_strings":["Institute of Acoustics,Key Laboratory of Speech Acoustics and Content Understanding"],"affiliations":[{"raw_affiliation_string":"Institute of Acoustics,Key Laboratory of Speech Acoustics and Content Understanding","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100335973","display_name":"Li Wang","orcid":"https://orcid.org/0000-0002-2204-5192"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Wang","raw_affiliation_strings":["Institute of Acoustics,Key Laboratory of Speech Acoustics and Content Understanding"],"affiliations":[{"raw_affiliation_string":"Institute of Acoustics,Key Laboratory of Speech Acoustics and Content Understanding","institution_ids":["https://openalex.org/I4210099069"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5010332632"],"corresponding_institution_ids":["https://openalex.org/I4210099069"],"apc_list":null,"apc_paid":null,"fwci":0.3103,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.64776841,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"146","last_page":"150"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.8687999844551086,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.8687999844551086,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dysarthria","display_name":"Dysarthria","score":0.791964054107666},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5181683301925659},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49067676067352295},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.4793732464313507},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4669087529182434},{"id":"https://openalex.org/keywords/audiology","display_name":"Audiology","score":0.41549789905548096},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.214165598154068},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.15305191278457642},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07152998447418213}],"concepts":[{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.791964054107666},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5181683301925659},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49067676067352295},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.4793732464313507},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4669087529182434},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.41549789905548096},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.214165598154068},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.15305191278457642},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07152998447418213}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800051","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2003171151","https://openalex.org/W2033068515","https://openalex.org/W2040972403","https://openalex.org/W2042105302","https://openalex.org/W2148326423","https://openalex.org/W2159739798","https://openalex.org/W2194775991","https://openalex.org/W2314395941","https://openalex.org/W2344936922","https://openalex.org/W2346340151","https://openalex.org/W2889469831","https://openalex.org/W2963155035","https://openalex.org/W2963446712","https://openalex.org/W3097777922","https://openalex.org/W3117926103","https://openalex.org/W3123500774","https://openalex.org/W3130967494","https://openalex.org/W3202749981","https://openalex.org/W4206187162","https://openalex.org/W4297267083","https://openalex.org/W4385245566","https://openalex.org/W4388118234","https://openalex.org/W6866580884"],"related_works":["https://openalex.org/W2331173358","https://openalex.org/W2969484279","https://openalex.org/W3160456149","https://openalex.org/W2168872498","https://openalex.org/W4400873482","https://openalex.org/W2329762060","https://openalex.org/W2517018229","https://openalex.org/W2351669973","https://openalex.org/W2312964388","https://openalex.org/W2980869992"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"an":[3,105],"automatic":[4,126],"dysarthria":[5,127],"severity":[6,24],"assessment":[7],"system":[8,15,116],"submitted":[9],"for":[10,47,125],"the":[11,23,29,54,60,68,99,114],"MDSA2024":[12],"challenge.":[13],"The":[14,56,95,110],"utilizes":[16],"audio":[17,48,73,82],"and":[18,41,83,92,120],"visual":[19,84],"features":[20],"to":[21,67,87],"classify":[22],"of":[25,31,108],"dysarthria.":[26],"We":[27,75],"investigate":[28],"effectiveness":[30],"different":[32],"acoustic":[33],"feature":[34],"combinations,":[35],"such":[36],"as":[37],"Mel":[38],"spectrogram,":[39],"filterbank":[40],"constant":[42],"Q":[43],"transform.":[44],"Different":[45],"encoders":[46],"data":[49],"processing":[50],"are":[51],"compared":[52,66],"in":[53,89],"experiments.":[55],"results":[57],"demonstrate":[58],"that":[59,113],"Conformer":[61,118],"encoder":[62,70,119],"achieves":[63],"superior":[64],"performance":[65],"Densenet":[69],"on":[71,98],"pure":[72],"features.":[74],"further":[76],"explore":[77],"model-level":[78,121],"fusion":[79,122],"by":[80],"combining":[81],"embeddings,":[85],"leading":[86],"improvements":[88],"precision\u2019":[90],"recall,":[91],"accuracy":[93],"metrics.":[94],"best-achieved":[96],"score":[97],"test":[100],"set":[101],"is":[102],"7.5579,":[103],"with":[104,117],"individual":[106],"F1-score":[107],"0.7028.":[109],"findings":[111],"suggest":[112],"proposed":[115],"holds":[123],"promise":[124],"assessment.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}